Exploring Active Learning in Meta-Learning: Enhancing Context Set Labeling
Not on the map. Why?
Abstract (arXiv)
Most meta-learning methods assume that the (very small) context set used to establish a new task at test time is passively provided. In some settings, however, it is feasible to actively select which points to label; the potential gain from a careful choice is substantial, but the setting requires major differences from typical active learning setups. We clarify the ways in which active meta-learning can be used to label a context set, depending on which parts of the meta-learning process use active learning. Within this framework, we propose a natural algorithm based on fitting Gaussian mixtures for selecting which points to label; though simple, the algorithm also has theoretical motivation. The proposed algorithm outperforms state-of-the-art active learning methods when used with various meta-learning algorithms across several benchmark datasets.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 46 of its 76 references that are in the map. First posted on arXiv 6 Nov 2023.
Builds on
46 of 76 references.
References · 46
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
- 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
- 2017Prototypical Networks for Few-shot Learningcited by 3,001
- 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
- 2016Matching Networks for One Shot Learningcited by 2,246
- 2020Meta-Learning in Neural Networks: A Surveycited by 944
- 2019Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descentcited by 732
- 2019A Closer Look at Few-shot Classificationcited by 679
- 2017The Implicit Bias of Gradient Descent on Separable Datacited by 649
- 2019Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Boundscited by 602
- 2020A Survey of Deep Active Learningcited by 547
34 more
- 2019Meta-Learning with Differentiable Convex Optimizationcited by 461
- 2018Meta-Learning for Semi-Supervised Few-Shot Classificationcited by 456
- 2018Conditional Neural Processescited by 421
- 2018TADAM: Task dependent adaptive metric for improved few-shot learningcited by 408
- 2018Meta-learning with differentiable closed-form solverscited by 395
- 2019Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAMLcited by 359
- 2018Neural Processescited by 307
- 2018How to train your MAMLcited by 306
- 2019Attentive Neural Processescited by 280
- 2019SimpleShot: Revisiting Nearest-Neighbor Classification for Few-Shot Learningcited by 194
- 2019Convolutional Conditional Neural Processescited by 139
- 2022Active Learning on a Budget: Opposite Strategies Suit High and Low Budgetscited by 131
- 2017Learning Active Learning from Datacited by 100
- 2017Learning how to Active Learn: A Deep Reinforcement Learning Approachcited by 79
- 2020learn2learn: A Library for Meta-Learning Researchcited by 69
- 2022Active Learning Through a Covering Lenscited by 62
- 2021Shallow Bayesian Meta Learning for Real-World Few-Shot Recognitioncited by 48
- 2020Unraveling Meta-Learning: Understanding Feature Representations for Few-Shot Taskscited by 47
- 2019Batch Active Learning Using Determinantal Point Processescited by 42
- 2018Few-Shot Learning with Metric-Agnostic Conditional Embeddingscited by 40
- 2020Data Augmentation for Meta-Learningcited by 38
- 2022Understanding Cross-Domain Few-Shot Learning Based on Domain Similarity and Few-Shot Difficultycited by 37
- 2022Making Look-Ahead Active Learning Strategies Feasible with Neural Tangent Kernelscited by 25
- 2020Probabilistic Active Meta-Learningcited by 23
- 2021Diversity Enhanced Active Learning with Strictly Proper Scoring Rulescited by 22
- 2016Active and Continuous Exploration with Deep Neural Networks and Expected Model Output Changescited by 18
- 2022What Matters For Meta-Learning Vision Regression Tasks?cited by 18
- 2021On Data Efficiency of Meta-learningcited by 16
- 2021On sensitivity of meta-learning to support datacited by 15
- 2020Is Support Set Diversity Necessary for Meta-Learning?cited by 14
- 2022The Effect of Diversity in Meta-Learningcited by 13
- 2022Active Few-Shot Learning with FASLcited by 11
- 2022An Embarrassingly Simple Approach to Semi-Supervised Few-Shot Learningcited by 10
- 2015Active Distance-Based Clustering using K-medoidscited by 8
Built on by
Citing papers per year: 2024: 1.
1 paper.